ESTIMATING THE DIAMETER OF TREE USING THE NEURO-FUZZY INFERENCE SYSTEM AND ARTIFICIAL NEURAL NETWORKS FROM THE TOTAL HEIGHT VARIABLE

Q4 Environmental Science

Floresta Pub Date : 2023-07-03 DOI:10.5380/rf.v53i4.86492

Gabriela Letícia Ramos Carvalho, Carlos Alberto Araújo Júnior, Emanuelly Magalhães Canabrava, A. M. Azevedo, Marcos Flávio Silveira Vasconcelos D Angelo, D. N. Cosenza

{"title":"ESTIMATING THE DIAMETER OF TREE USING THE NEURO-FUZZY INFERENCE SYSTEM AND ARTIFICIAL NEURAL NETWORKS FROM THE TOTAL HEIGHT VARIABLE","authors":"Gabriela Letícia Ramos Carvalho, Carlos Alberto Araújo Júnior, Emanuelly Magalhães Canabrava, A. M. Azevedo, Marcos Flávio Silveira Vasconcelos D Angelo, D. N. Cosenza","doi":"10.5380/rf.v53i4.86492","DOIUrl":null,"url":null,"abstract":"Studies that seek to identify potential techniques for obtaining diameter values at 1.30 m from the ground from tree height data are necessary, especially when considering the use of airborne Lidar in forest inventory activity. In this sense, this work aimed to evaluate two artificial intelligence tools for this purpose, namely the neuro-fuzzy inference systems and the artificial neural networks. Four models were tested to obtain estimates for the diameter variable, which were prepared by combining the independent variables useful area per plant, age and height. After processing, the statistics of bias, square root of the mean squared error in percentage, correlation and mean percentage error were calculated, in addition to the preparation of scatter plots and histogram of residues. It was observed that, for the estimation of the diameter in both techniques, the use of the model with all independent variables obtained the best values for the analysis statistics. It can be concluded that both tools can be used to estimate the diameter, with the neuro-fuzzy inference system being more suitable for its processing speed and small variability between the values obtained in different training sessions for the same database.","PeriodicalId":53573,"journal":{"name":"Floresta","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Floresta","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5380/rf.v53i4.86492","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Environmental Science","Score":null,"Total":0}

引用次数: 0

Abstract

Studies that seek to identify potential techniques for obtaining diameter values at 1.30 m from the ground from tree height data are necessary, especially when considering the use of airborne Lidar in forest inventory activity. In this sense, this work aimed to evaluate two artificial intelligence tools for this purpose, namely the neuro-fuzzy inference systems and the artificial neural networks. Four models were tested to obtain estimates for the diameter variable, which were prepared by combining the independent variables useful area per plant, age and height. After processing, the statistics of bias, square root of the mean squared error in percentage, correlation and mean percentage error were calculated, in addition to the preparation of scatter plots and histogram of residues. It was observed that, for the estimation of the diameter in both techniques, the use of the model with all independent variables obtained the best values for the analysis statistics. It can be concluded that both tools can be used to estimate the diameter, with the neuro-fuzzy inference system being more suitable for its processing speed and small variability between the values obtained in different training sessions for the same database.

查看原文本刊更多论文

用神经模糊推理系统和人工神经网络从总高度变量估计树的直径

有必要进行研究，以确定从树高数据中获得距地面1.30米直径值的潜在技术，特别是在考虑在森林清查活动中使用机载激光雷达时。从这个意义上说，这项工作旨在评估两种人工智能工具，即神经模糊推理系统和人工神经网络。利用单株有用面积、树龄和高度等自变量，对4个模型进行了检验，得到了直径变量的估计值。处理后，计算偏差统计量、均方误差的平方根百分比统计量、相关性统计量和平均百分比误差统计量，并制作残差的散点图和直方图。我们观察到，对于两种技术的直径估计，使用具有所有自变量的模型获得了分析统计的最佳值。可以得出结论，这两种工具都可以用来估计直径，神经模糊推理系统更适合于处理速度快，并且在同一数据库的不同训练阶段获得的值之间的变异性较小。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Floresta Environmental Science-Nature and Landscape Conservation

CiteScore

0.80

自引率

0.00%

发文量

期刊介绍： Revista Floresta admits articles of scientific contribution in Forest Science, in the areas of Nature Conservation, Economy and Forest Policy, Forest Management, Silviculture and Wood Technology. The main task is to promote and divulgate the development of Forest Science in Brazil and in the world. Articles published in Revista Floresta are under total responsibility of the authors, who are aware that they are original studies. It remains implicit that articles were not submitted for publication to any other divulgation media. It remains explicit the agreement of authors to norms of the journal and, along the development of their work, the observance of ethic aspects and respect of the current copyright legislation.